No abstract

No abstract

SporthesiaVideo Processor "…gets him close to the backhand court" Video Commentary "Federer looks to be covering the crosscourt, which gets him close to the backhand court. " + "Feder looks to be covering the crosscourt…" a b cFig. 1: Sporthesia takes raw video footage and commentary text of racket-based sports as input, and outputs an augmented video. To achieve this, three key steps are taken: 1) detecting the visualizable entities in the text, 2) mapping the entities to visualizations, and 3) scheduling the visualizations to play with the raw video.

No abstract

Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited samples for some novel sub-categories, leading to the fine-grained few shot learning (FG-FSL) setting. To address this challenging task, we propose a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator. The former aims to remove image background, which tends to increase the difficulty of fine-grained image classification as it amplifies the intra-class variance while reduces inter-class variance. The latter transforms the posture of the foreground object to generate additional samples for the novel sub-category. As a data augmentation method, FOT can be conveniently applied to any existing few shot learning algorithm and greatly improve its performance on FG-FSL tasks. In particular, in combination with FOT, simple fine-tuning baseline methods can be competitive with the state-of-the-art methods both in inductive setting and transductive setting. Moreover, FOT can further boost the performances of latest excellent methods and bring them up to the new state-of-the-art. In addition, we also show the effectiveness of FOT on general FSL tasks.